Pepys MCP Server
pepys-mcp
npm
v0.1.1
Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Pepys transcription MCP server (stdio) – transcribe hours-long audio/video, diarization, timed SRT/VTT, paste-a-link (YouTube/podcast), batch, word-level export. Never trains on your audio.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 5 = 95. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 3
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([transcribe, get_transcription, list_podcast_episodes]) co-exist with external-action tools ([transcribe, upload_file]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [transcribe, get_transcription, list_podcast_episodes] → sinks [transcribe, upload_file]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow transcribe → transcribe
medium Unconstrained URL/host parameter "url" on "transcribe"MTC-CAP-007
Tool "transcribe" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool transcribe · inputSchema.properties.url
medium Unconstrained URL/host parameter "feed_url" on "list_podcast_episodes"MTC-CAP-007
Tool "list_podcast_episodes" takes a URL/host parameter "feed_url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool list_podcast_episodes · inputSchema.properties.feed_url
Tools 9
Each tool and what it can reach — statically extracted from the published source.
transcribeingests untrusted inputnetwork egressget_transcriptioningests untrusted inputlist_podcast_episodesingests untrusted inputupload_filenetwork egressexport_transcriptno sensitive capabilityget_credit_balanceno sensitive capabilitylist_transcriptionsno sensitive capabilitysearch_transcriptno sensitive capabilitytranscribe_podcast_feedno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (9 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.1.1 latest |
A 95/100 | 3 | 1.13.0 | 2026-09-08 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan pepys-mcp --onlineMore in Other
A Model Context Protocol server implementation for AdGuard Home that enables AI agents to query and manage DNS records, filtering rules and more
Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.
MCP server with Airtable integration
A free one-minute reset for people, delivered by AI, with no account or personal data.
Access SEC filings efficiently, save time and tokens, and get cited answers.
A smart [MCP](https://modelcontextprotocol.io) server for [AniList](https://anilist.co) that gets your anime/manga taste - not just API calls.